rlundqvist/exp11-cot-leakage

Chain-of-Thought Leakage RL TL;DR What we're doing. Online GRPO on a 49B model (Tim Hua's "Wood organism" — a Nemotron Super 49B fine-tuned to behave differently when it thinks it's being evaluated by Wood Labs). The reward model is gpt-oss-120b reading Anthropic's Constitution as a system prompt, with the model's chain-of-thought visible. Each rollout gets two ratings — one with CoT shown to the judge, one with only the post-</think> response. The reward we train… See the full description on the dataset page: https://huggingface.co/datasets/rlundqvist/exp11-cot-leakage.

<iframe src="https://silytics.si/embed/item/68b767d8-28db-44d5-bcb7-8428a19323b0" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Silytics shows public metadata from Hugging Face and links to the original. Information may be incomplete or out of date. Last refreshed 19 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.